# SCALE: Self-Correcting Visual Navigation for Mobile Robots via Anti-Novelty Estimation

arXiv: https://arxiv.org/abs/2404.10675 · HTML: https://mlsanity.com/paper/2404.10675/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 40 references that are in the map.
- First posted on arXiv 16 Apr 2024.

## Builds on (most cited first, 23 of 23)

- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [Offline Reinforcement Learning with Implicit Q-Learning](https://mlsanity.com/paper/2110.06169/) (2021)
- [Hindsight Experience Replay](https://mlsanity.com/paper/1707.01495/) (2017)
- [Exploration by Random Network Distillation](https://mlsanity.com/paper/1810.12894/) (2018)
- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)
- [Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning](https://mlsanity.com/paper/1910.00177/) (2019)
- [Learning to Explore using Active Neural SLAM](https://mlsanity.com/paper/2004.05155/) (2020)
- [ViNT: A Foundation Model for Visual Navigation](https://mlsanity.com/paper/2306.14846/) (2023)
- [Semi-parametric Topological Memory for Navigation](https://mlsanity.com/paper/1803.00653/) (2018)
- [Planning with Goal-Conditioned Policies](https://mlsanity.com/paper/1911.08453/) (2019)
- [Rapid Exploration for Open-World Navigation with Latent Goal Models](https://mlsanity.com/paper/2104.05859/) (2021)
- [FILM: Following Instructions in Language with Modular Methods](https://mlsanity.com/paper/2110.07342/) (2021)
- [Neural Map: Structured Memory for Deep Reinforcement Learning](https://mlsanity.com/paper/1702.08360/) (2017)
- [No RL, No Simulation: Learning to Navigate without Navigating](https://mlsanity.com/paper/2110.09470/) (2021)
- [Anti-Exploration by Random Network Distillation](https://mlsanity.com/paper/2301.13616/) (2023)
- [Topological Semantic Graph Memory for Image-Goal Navigation](https://mlsanity.com/paper/2209.08274/) (2022)
- [Offline Reinforcement Learning for Visual Navigation](https://mlsanity.com/paper/2212.08244/) (2022)
- [Generalization with Lossy Affordances: Leveraging Broad Offline Data for Learning Visuomotor Tasks](https://mlsanity.com/paper/2210.06601/) (2022)
- [Visual Affordance Prediction for Guiding Robot Exploration](https://mlsanity.com/paper/2305.17783/) (2023)

## Built on by (most cited first, 1 of 1)

- [NOLO: Navigate Only Look Once](https://mlsanity.com/paper/2408.01384/) (2024)

## Abstract (arXiv)

Although visual navigation has been extensively studied using deep reinforcement learning, online learning for real-world robots remains a challenging task. Recent work directly learned from offline dataset to achieve broader generalization in the real-world tasks, which, however, faces the out-of-distribution (OOD) issue and potential robot localization failures in a given map for unseen observation. This significantly drops the success rates and even induces collision. In this paper, we present a self-correcting visual navigation method, SCALE, that can autonomously prevent the robot from the OOD situations without human intervention. Specifically, we develop an image-goal conditioned offline reinforcement learning method based on implicit Q-learning (IQL). When facing OOD observation, our novel localization recovery method generates the potential future trajectories by learning from the navigation affordance, and estimates the future novelty via random network distillation (RND). A tailored cost function searches for the candidates with the least novelty that can lead the robot to the familiar places. We collect offline data and conduct evaluation experiments in three real-world urban scenarios. Experiment results show that SCALE outperforms the previous state-of-the-art methods for open-world navigation with a unique capability of localization recovery, significantly reducing the need for human intervention. Code is available at https://github.com/KubeEdge4Robotics/ScaleNav.